NVIDIA L4 vs AMD Radeon Pro Vega 48

Comparative analysis of NVIDIA L4 and AMD Radeon Pro Vega 48 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: Geekbench - OpenCL, PassMark - G2D Mark, PassMark - G3D Mark, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

NVIDIA L4

AMD Radeon Pro Vega 48

Differences

Reasons to consider the NVIDIA L4

Around 57% higher boost clock speed: 2040 MHz vs 1300 MHz
Around 96% higher texture fill rate: 489.6 GTexel/s vs 249.6 GTexel/s
2.5x more pipelines: 7680 vs 3072
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 5 nm vs 14 nm
173.6x lower typical power consumption: 72 Watt vs 12500 million
3x more maximum memory size: 24 GB vs 8 GB
Around 99% higher memory clock speed: 1563 MHz, 12.5 Gbps effective vs 786 MHz (1572 MHz effective)
2.6x better performance in Geekbench - OpenCL: 140723 vs 53937

Specifications (specs)
Boost clock speed	2040 MHz vs 1300 MHz
Texture fill rate	489.6 GTexel/s vs 249.6 GTexel/s
Pipelines	7680 vs 3072
Manufacturing process technology	5 nm vs 14 nm
Thermal Design Power (TDP)	72 Watt vs 12500 million
Maximum memory size	24 GB vs 8 GB
Memory clock speed	1563 MHz, 12.5 Gbps effective vs 786 MHz (1572 MHz effective)
Benchmarks
Geekbench - OpenCL	140723 vs 53937

Reasons to consider the AMD Radeon Pro Vega 48

Around 51% higher core clock speed: 1200 MHz vs 795 MHz
4x better performance in PassMark - G2D Mark: 784 vs 196
Around 88% better performance in PassMark - G3D Mark: 11300 vs 6006

Specifications (specs)
Core clock speed	1200 MHz vs 795 MHz
Benchmarks
PassMark - G2D Mark	784 vs 196
PassMark - G3D Mark	11300 vs 6006

Compare benchmarks

GPU 1: NVIDIA L4
GPU 2: AMD Radeon Pro Vega 48

Geekbench - OpenCL

GPU 1

GPU 2

140723

53937

PassMark - G2D Mark

GPU 1

GPU 2

196

784

PassMark - G3D Mark

GPU 1

GPU 2

6006

11300

Name	NVIDIA L4	AMD Radeon Pro Vega 48
Geekbench - OpenCL	140723	53937
PassMark - G2D Mark	196	784
PassMark - G3D Mark	6006	11300
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		135.416
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		3063.269
CompuBench 1.5 Desktop - T-Rex (Frames/s)		12.678
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		883.876
GFXBench 4.0 - Car Chase Offscreen (Frames)		11925
GFXBench 4.0 - Manhattan (Frames)		3947
GFXBench 4.0 - T-Rex (Frames)		10411
GFXBench 4.0 - Car Chase Offscreen (Fps)		11925
GFXBench 4.0 - Manhattan (Fps)		3947
GFXBench 4.0 - T-Rex (Fps)		10411

Compare specifications (specs)

	NVIDIA L4	AMD Radeon Pro Vega 48
Essentials
Architecture	Ada Lovelace	Vega 10 PRO
Code name	AD104	Greenland
Place in performance rating	230	232
GCN generation		GCN 5.0
Launch date		19 March 2019
Type		Desktop
Technical info
Boost clock speed	2040 MHz	1300 MHz
Core clock speed	795 MHz	1200 MHz
Manufacturing process technology	5 nm	14 nm
Pipelines	7680	3072
Pixel fill rate	163.2 GPixel/s	83.20 GPixel/s
Texture fill rate	489.6 GTexel/s	249.6 GTexel/s
Thermal Design Power (TDP)	72 Watt	12500 million
Transistor count	35800 million
Peak Double Precision (FP64) Performance		499.2 GFLOPS
Peak Half Precision (FP16) Performance		15.97 TFLOPS
Peak Single Precision (FP32) Performance		7.987 TFLOPS
Video outputs and ports
Display Connectors	1x HDMI 2.1, 3x DisplayPort 1.4a	No outputs
Compatibility, dimensions and requirements
Form factor	Single-slot
Interface	PCIe 4.0 x16	PCIe 3.0 x16
Length	169 mm, 6.7 inches
Recommended system power (PSU)	250 Watt
Supplementary power connectors	1x 16-pin
Width	56 mm, 2.2 inches
API support
DirectX	12 Ultimate (12_2)	12.1
OpenCL	3.0	2.0
OpenGL	4.6	4.6
Shader Model	6.7	6.3
Vulkan
Memory
Maximum RAM amount	24 GB	8 GB
Memory bandwidth	300.1 GB/s	402.4 GB/s
Memory bus width	192 bit	2048 bit
Memory clock speed	1563 MHz, 12.5 Gbps effective	786 MHz (1572 MHz effective)
Memory type	GDDR6	HBM2
High bandwidth memory (HBM)
Technologies
Unified Video Decoder (UVD)
Video Code Engine (VCE)